Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MadAppGang/magus --skill hybrid-debugginggit clone --depth 1 https://github.com/MadAppGang/magusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/madappgang/magus/hybrid-debugging)<a href="https://agentmods.dev/skills/madappgang/magus/hybrid-debugging"><img src="https://agentmods.dev/badge/skills/madappgang/magus/hybrid-debugging.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.02886 |
| Opus 5 | $0.00022 | $0.01443 |
| Sonnet 5 | $0.00009 | $0.00577 |
| Haiku 4.5 | $0.00004 | $0.00289 |
Grade A, and why
hybrid-debugging scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hybrid Debugging: Browser Use + claude-in-chrome
Patterns for combining Browser Use MCP tools with claude-in-chrome to achieve full-spectrum browser debugging.
Core principle: Browser Use and claude-in-chrome have complementary capabilities. Neither covers everything alone. Hybrid workflows combine their strengths.
1. Tool Capability Map
| Capability | Browser Use | claude-in-chrome |
|---|---|---|
| Navigate to URL | browser_navigate |
Tab management only |
| Click elements | browser_click (by index) |
computer (by coordinate) |
| Type into inputs | browser_type (by index) |
computer (keyboard) |
| Get DOM element map | browser_get_state |
read_page (text extract) |
| Read raw HTML | browser_get_html |
read_page |
| Take screenshot | browser_screenshot |
computer (screenshot) |
| Capture full-page screenshot | browser_screenshot(full_page=True) |
Not available |
| Scroll page | browser_scroll |
computer (scroll) |
| Read console errors | Not available | read_console_messages |
| Read network requests | Not available | read_network_requests |
| Execute JavaScript | Not available (no eval tool) | javascript_tool |
| Resize viewport | Via agent only | javascript_tool (resizeTo) |
| Record GIF of interaction | Not available | gif_creator |
| Autonomous agent mode | retry_with_browser_use_agent |
Not available |
| Multi-tab session | browser_navigate(new_tab=True) |
Tab enumeration only |
| Export/import session cookies | browser_export/import_session |
Not available |
| Work on headless browser | Yes (Chromium) | No (requires headed Chrome) |
| Work on developer's Chrome | No | Yes (attaches to running Chrome) |
2. Detecting claude-in-chrome Availability
Before using hybrid patterns, verify claude-in-chrome is accessible. It requires Chrome to be running with the Claude Chrome extension installed.
# Probe for claude-in-chrome availability
mcp__claude-in-chrome__tabs_context_mcp()
→ If successful: returns list of open Chrome tabs → claude-in-chrome IS available
→ If error/timeout: claude-in-chrome NOT available → fall back to Browser Use-only mode
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 290 lines · 43 tokens per session scan A c0651f049956
hybrid-debugging is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 2,886 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.